Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 129 581 624 717 808 600 254 319 135 295 157  77 147 942 233  87 182 900 955 194
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 194 157 942 581 129 624  NA  NA 900 808  77 233 182 254 147  NA 295  87 600 135 717 319 955
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 3 2 3 3 3 4 2 3 3 2
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "e" "x" "y" "o" "z" "U" "Y" "S" "O" "B"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 14 19
which( manyNumbersWithNA > 900 )
[1]  3 23
which( is.na( manyNumbersWithNA ) )
[1]  7  8 16

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 942 955
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 942 955
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 942 955

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "U" "Y" "S" "O" "B"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "e" "x" "y" "o" "z"
manyNumbers %in% 300:600
 [1] FALSE  TRUE FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1] 2 6 8
sum( manyNumbers %in% 300:600 )
[1] 3

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "small" "large" "large" "small" "large" NA      NA      "large" "large" "small" "small" "small" "small" "small"
[16] NA      "small" "small" "large" "small" "large" "small" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "small"   "large"   "large"   "small"   "large"   "UNKNOWN" "UNKNOWN" "large"   "large"   "small"   "small"  
[13] "small"   "small"   "small"   "UNKNOWN" "small"   "small"   "large"   "small"   "large"   "small"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0   0 942 581   0 624  NA  NA 900 808   0   0   0   0   0  NA   0   0 600   0 717   0 955

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 3 2 4
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  3  2  4
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 23
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 955
which.min( manyNumbersWithNA )
[1] 11
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 77
range( manyNumbersWithNA, na.rm = TRUE )
[1]  77 955

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 194 157 942 581 129 624  NA  NA 900 808  77 233 182 254 147  NA 295  87 600 135 717 319 955
sort( manyNumbersWithNA )
 [1]  77  87 129 135 147 157 182 194 233 254 295 319 581 600 624 717 808 900 942 955
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  77  87 129 135 147 157 182 194 233 254 295 319 581 600 624 717 808 900 942 955  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 955 942 900 808 717 624 600 581 319 295 254 233 194 182 157 147 135 129  87  77  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 194 157 942 581 129
order( manyNumbersWithNA[1:5] )
[1] 5 2 1 4 3
rank( manyNumbersWithNA[1:5] )
[1] 3 2 5 4 1
sort( mixedLetters )
 [1] "B" "e" "o" "O" "S" "U" "x" "y" "Y" "z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  5.0  8.5  5.0 10.0  1.5  1.5  5.0  8.5  5.0  5.0
rank( manyDuplicates, ties.method = "min" )
 [1]  3  8  3 10  1  1  3  8  3  3
rank( manyDuplicates, ties.method = "random" )
 [1]  7  8  5 10  2  1  6  9  4  3

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000  0.5207953  2.5394769  1.3623847  1.2349935  1.4918065  1.5235200
[12] -0.5732543 -1.5278983  0.1827449  0.7606266
round( v, 0 )
 [1] -1  0  0  0  1  1  3  1  1  1  2 -1 -2  0  1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.5  2.5  1.4  1.2  1.5  1.5 -0.6 -1.5  0.2  0.8
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.52  2.54  1.36  1.23  1.49  1.52 -0.57 -1.53  0.18  0.76
floor( v )
 [1] -1 -1  0  0  1  0  2  1  1  1  1 -1 -2  0  0
ceiling( v )
 [1] -1  0  0  1  1  1  3  2  2  2  2  0 -1  1  1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC